Yilun Zhao

Cross-attentive MLLMs already solve the attribute-binding failures that cripple embedding models—and distilling their soft multi-level ranking distributions via Rank-KL unlocks that reasoning for bi-encoders without degrading standard recall.

Current GUI world models often produce visually appealing screens but lack the contextual consistency needed for effective multi-step agent interactions.

Smaller language models can efficiently replace larger ones in rubric-based reinforcement learning, achieving competitive performance with significantly reduced computational costs.

LLM-generated research ideas are systematically narrower and more focused than those of human researchers, revealing a significant gap in creative breadth.